INDEX

Explanations

technical terms and programming keywords

oai_token-act-pair · gpt-3.5-turbo

technical terms and specific nouns relating to systems, processes, or entities

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 destro

-0.60

regor

-0.56

©¶æ

-0.56

 Sunshine

-0.55

 Defin

-0.55

enegger

-0.54

PsyNetMessage

-0.53

schild

-0.52

-+-+

-0.51

 Definitive

-0.50

POSITIVE LOGITS

wise

0.60

:=

0.54

 versa

0.52

)!

0.51

ania

0.50

 extraord

0.48

 replies

0.48

tis

0.48

 congr

0.48

!:

0.48

Activations Density 0.476%

technical terms and programming keywords

technical terms and specific nouns relating to systems, processes, or entities

No Known Activations